End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,216 @@
+---
+library_name: peft
+license: mit
+base_model: fxmarty/tiny-random-GemmaForCausalLM
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: f51bfe77-a6eb-4b31-8db3-03587638137c
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+adapter: lora
+base_model: fxmarty/tiny-random-GemmaForCausalLM
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 5357759852985b4d_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/5357759852985b4d_train_data.json
+  type:
+    field_input: Complex_CoT
+    field_instruction: Question
+    field_output: Response
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device_map: auto
+do_eval: true
+early_stopping_patience: 3
+eval_batch_size: 4
+eval_max_new_tokens: 128
+eval_steps: 200
+eval_table_size: null
+evals_per_epoch: null
+flash_attention: true
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+group_by_length: true
+hub_model_id: baby-dev/f51bfe77-a6eb-4b31-8db3-03587638137c
+hub_strategy: end
+learning_rate: 0.0002
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 50
+lora_alpha: 64
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 32
+lora_target_linear: true
+lr_scheduler: constant
+max_grad_norm: 1.0
+max_memory:
+  0: 75GB
+max_steps: 23974
+micro_batch_size: 4
+mlflow_experiment_name: /tmp/5357759852985b4d_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 10
+optim_args:
+  adam_beta1: 0.9
+  adam_beta2: 0.95
+  adam_epsilon: 1e-5
+optimizer: adamw_bnb_8bit
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 200
+saves_per_epoch: null
+sequence_len: 512
+strict: false
+tf32: true
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: null
+wandb_mode: online
+wandb_name: 4825c224-af5c-46aa-8cf7-640b49b5a593
+wandb_project: SN56-45
+wandb_run: your_name
+wandb_runid: 4825c224-af5c-46aa-8cf7-640b49b5a593
+warmup_steps: 50
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# f51bfe77-a6eb-4b31-8db3-03587638137c
+
+This model is a fine-tuned version of [fxmarty/tiny-random-GemmaForCausalLM](https://huggingface.co/fxmarty/tiny-random-GemmaForCausalLM) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 12.3695
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_steps: 50
+- training_steps: 14470
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| No log        | 0.0007 | 1     | 12.4576         |
+| 12.4008       | 0.1382 | 200   | 12.4003         |
+| 12.395        | 0.2764 | 400   | 12.3943         |
+| 12.3938       | 0.4147 | 600   | 12.3938         |
+| 12.3923       | 0.5529 | 800   | 12.3918         |
+| 12.3906       | 0.6911 | 1000  | 12.3871         |
+| 12.3865       | 0.8293 | 1200  | 12.3827         |
+| 12.383        | 0.9675 | 1400  | 12.3802         |
+| 12.3819       | 1.1057 | 1600  | 12.3794         |
+| 12.3811       | 1.2440 | 1800  | 12.3783         |
+| 12.3801       | 1.3822 | 2000  | 12.3778         |
+| 12.3811       | 1.5204 | 2200  | 12.3772         |
+| 12.3805       | 1.6586 | 2400  | 12.3774         |
+| 12.3807       | 1.7968 | 2600  | 12.3770         |
+| 12.3804       | 1.9350 | 2800  | 12.3774         |
+| 12.3793       | 2.0733 | 3000  | 12.3764         |
+| 12.38         | 2.2115 | 3200  | 12.3761         |
+| 12.3799       | 2.3497 | 3400  | 12.3763         |
+| 12.3795       | 2.4879 | 3600  | 12.3758         |
+| 12.3809       | 2.6261 | 3800  | 12.3757         |
+| 12.3785       | 2.7643 | 4000  | 12.3757         |
+| 12.3779       | 2.9026 | 4200  | 12.3755         |
+| 12.379        | 3.0408 | 4400  | 12.3753         |
+| 12.3781       | 3.1790 | 4600  | 12.3754         |
+| 12.3778       | 3.3172 | 4800  | 12.3750         |
+| 12.3765       | 3.4554 | 5000  | 12.3751         |
+| 12.3777       | 3.5936 | 5200  | 12.3748         |
+| 12.3765       | 3.7319 | 5400  | 12.3749         |
+| 12.3778       | 3.8701 | 5600  | 12.3746         |
+| 12.3788       | 4.0083 | 5800  | 12.3746         |
+| 12.3768       | 4.1465 | 6000  | 12.3746         |
+| 12.3774       | 4.2847 | 6200  | 12.3742         |
+| 12.3774       | 4.4229 | 6400  | 12.3741         |
+| 12.3766       | 4.5612 | 6600  | 12.3739         |
+| 12.3775       | 4.6994 | 6800  | 12.3738         |
+| 12.3769       | 4.8376 | 7000  | 12.3740         |
+| 12.3769       | 4.9758 | 7200  | 12.3737         |
+| 12.3774       | 5.1140 | 7400  | 12.3736         |
+| 12.3754       | 5.2522 | 7600  | 12.3733         |
+| 12.3759       | 5.3905 | 7800  | 12.3728         |
+| 12.3742       | 5.5287 | 8000  | 12.3728         |
+| 12.3764       | 5.6669 | 8200  | 12.3724         |
+| 12.3766       | 5.8051 | 8400  | 12.3721         |
+| 12.3761       | 5.9433 | 8600  | 12.3720         |
+| 12.3746       | 6.0815 | 8800  | 12.3714         |
+| 12.3749       | 6.2198 | 9000  | 12.3710         |
+| 12.3739       | 6.3580 | 9200  | 12.3710         |
+| 12.3743       | 6.4962 | 9400  | 12.3709         |
+| 12.3748       | 6.6344 | 9600  | 12.3706         |
+| 12.3723       | 6.7726 | 9800  | 12.3706         |
+| 12.3738       | 6.9109 | 10000 | 12.3703         |
+| 12.3724       | 7.0491 | 10200 | 12.3702         |
+| 12.3723       | 7.1873 | 10400 | 12.3696         |
+| 12.3728       | 7.3255 | 10600 | 12.3697         |
+| 12.3736       | 7.4637 | 10800 | 12.3694         |
+| 12.3728       | 7.6019 | 11000 | 12.3698         |
+| 12.3735       | 7.7402 | 11200 | 12.3695         |
+| 12.3732       | 7.8784 | 11400 | 12.3695         |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "fxmarty/tiny-random-GemmaForCausalLM",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9f03ae60f8d4571b39d77e8320ac0259f5044ddf12bcf82d4aaa01e8fb32c6b
+size 41112

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e3d1e282e51d7a9d49f83782ecc73927621bf04a29d07f9d7174783f86f707
+size 37352

config.json

@@ -0,0 +1,30 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "fxmarty/tiny-random-GemmaForCausalLM",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 8,
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 2,
+  "max_position_embeddings": 512,
+  "model_type": "gemma",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 256000
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a63c485bbbab0efcfc1ffe32fd177108a9f70be1875ea3aacad3c4f064a5974b
+size 34315097

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e346f067d7aebd38c637a176f84ba9a89cca69f4c58ec73b2813eabf3e28fb
+size 6776